End of training

README.md

@@ -0,0 +1,105 @@
+---
+license: apache-2.0
+base_model: jonatasgrosman/wav2vec2-large-xlsr-53-english
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: wav2vec2-large-xlsr-53-english-finetuned-ravdess-v6
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# wav2vec2-large-xlsr-53-english-finetuned-ravdess-v6
+
+This model is a fine-tuned version of [jonatasgrosman/wav2vec2-large-xlsr-53-english](https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-english) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1552
+- Accuracy: 0.5660
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.079         | 0.07  | 10   | 2.0767          | 0.1667   |
+| 2.0728        | 0.14  | 20   | 2.0719          | 0.1389   |
+| 2.0713        | 0.21  | 30   | 2.0576          | 0.1562   |
+| 2.056         | 0.28  | 40   | 2.0382          | 0.1181   |
+| 2.0759        | 0.35  | 50   | 2.0160          | 0.2778   |
+| 2.0117        | 0.42  | 60   | 1.9332          | 0.2778   |
+| 1.8598        | 0.49  | 70   | 1.8759          | 0.2882   |
+| 1.9277        | 0.56  | 80   | 1.8321          | 0.2812   |
+| 1.7897        | 0.62  | 90   | 1.7278          | 0.3819   |
+| 1.8157        | 0.69  | 100  | 1.7270          | 0.3646   |
+| 1.9104        | 0.76  | 110  | 1.6997          | 0.3021   |
+| 1.8557        | 0.83  | 120  | 1.6664          | 0.4271   |
+| 1.8803        | 0.9   | 130  | 1.7943          | 0.3021   |
+| 1.7548        | 0.97  | 140  | 1.8016          | 0.3021   |
+| 1.7166        | 1.04  | 150  | 1.6303          | 0.3785   |
+| 1.7237        | 1.11  | 160  | 1.6330          | 0.4132   |
+| 1.7228        | 1.18  | 170  | 1.5905          | 0.4306   |
+| 1.5683        | 1.25  | 180  | 1.5216          | 0.4340   |
+| 1.716         | 1.32  | 190  | 1.4973          | 0.4306   |
+| 1.562         | 1.39  | 200  | 1.5994          | 0.3715   |
+| 1.5617        | 1.46  | 210  | 1.5699          | 0.4236   |
+| 1.6539        | 1.53  | 220  | 1.5024          | 0.3993   |
+| 1.58          | 1.6   | 230  | 1.4787          | 0.4132   |
+| 1.5107        | 1.67  | 240  | 1.4252          | 0.4444   |
+| 1.5934        | 1.74  | 250  | 1.4125          | 0.4444   |
+| 1.54          | 1.81  | 260  | 1.4032          | 0.4236   |
+| 1.4717        | 1.88  | 270  | 1.3636          | 0.4896   |
+| 1.5257        | 1.94  | 280  | 1.5080          | 0.4306   |
+| 1.4537        | 2.01  | 290  | 1.3346          | 0.4757   |
+| 1.356         | 2.08  | 300  | 1.3636          | 0.4653   |
+| 1.3572        | 2.15  | 310  | 1.3122          | 0.4757   |
+| 1.2657        | 2.22  | 320  | 1.2927          | 0.5174   |
+| 1.4931        | 2.29  | 330  | 1.3161          | 0.5382   |
+| 1.3314        | 2.36  | 340  | 1.3248          | 0.5      |
+| 1.375         | 2.43  | 350  | 1.2859          | 0.5521   |
+| 1.3316        | 2.5   | 360  | 1.2747          | 0.5556   |
+| 1.1443        | 2.57  | 370  | 1.2243          | 0.5625   |
+| 1.3866        | 2.64  | 380  | 1.2122          | 0.5590   |
+| 1.3274        | 2.71  | 390  | 1.2192          | 0.5174   |
+| 1.1248        | 2.78  | 400  | 1.1993          | 0.5278   |
+| 1.1337        | 2.85  | 410  | 1.1746          | 0.5556   |
+| 1.1394        | 2.92  | 420  | 1.1603          | 0.5625   |
+| 1.2199        | 2.99  | 430  | 1.1553          | 0.5660   |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,136 @@
+{
+  "_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-english",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "neutral",
+    "1": "calm",
+    "2": "happy",
+    "3": "sad",
+    "4": "angry",
+    "5": "fearful",
+    "6": "disgust",
+    "7": "surprised"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "angry": "4",
+    "calm": "1",
+    "disgust": "6",
+    "fearful": "5",
+    "happy": "2",
+    "neutral": "0",
+    "sad": "3",
+    "surprised": "7"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 33,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833d6ac3190a529dfe6c534b8e14dcc6a1ff537436cd01e2ebab008abe29266f
+size 1262960309

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f37c29b4f85ebf67124baad49b25750790676dc7a8311df8d31c97966ef66435
+size 4091